Post Job Free

Resume

Sign in

Hadoop Developer Active Directory

Location:
Alpharetta, GA
Posted:
May 29, 2021

Contact this candidate

Resume:

AKHIL NOONEY

940-***-**** admsz2@r.postjobfree.com http://linkedin.com/in/akhilnooney

PROFILE SUMMARY

• Worked on Agile methodology which includes Daily Scrum meetings, Sprint Planning & Retrospective meetings to meet customer expectations, timelines with quality deliverables.

• Experience in creating Artificial Intelligence applications with Machine Learning, Deep Learning, NLP with Python.

• Deep Learning Techniques include ANN, CNN, RNN, GoogleNet, ResNet, LSTM, GANs, VAEs, Pixel CNN.

• Skilled in libraries such as Pytorch Keras, Tensorflow, Sklearn, Numpy, Pandas, Matplotlib, Tableau for Data Visualization.

• Experience in Big Data technologies like Map Reduce, Sqoop, Hive, Spark.

• Knowledge of working with NoSQL databases like MongoDB and SQL databases like MySQL and Oracle.

• Worked Independently for Deployment of Models using Dockers and Kubernetes In AWS cloud, Google Cloud and Azure.

• Expertise in manipulating and analyzing complex, high-volume, high-dimensionality data from varying data sources and big data sources.

EDUCATION

Master’s in Data science August 2019 – April 2021

University of North Texas, Denton Texas. CGPA: 4.0 Bachelor of Technology in Computer Science and Engineering 2012-2016 CGPA: 3.21 CERTIFICATIONS

• Tableau Desktop Specialist 2020.01

WORK EXPERIENCE

City of Hope – Data Science Intern, USA May 2020 – August 2020

• Worked on an Agile (Scrum) Development Team to deliver regular updates to the business team and project manager.

• Deeper understanding of Machine learning models, Deep learning networks like GoogleNet, ResNet, LSTM and their applications.

• Implemented deep learning models like GANs, VAEs, Pixel CNN to generate both the structured and unstructured data.

• Developed a simple Web Application using “Streamlit” framework to automate the generation of synthetic data for end users.

• Used SHAP and LIME models on Synthetic tabular data for getting feature importance. Tata Consultancy Services Private Limited, India 2017-2019 Hadoop Developer August 2017- August 2019

• Worked in Agile-Scrum development methodology to ensure delivery of high-quality work with monthly iteration, also involved in sprint planning and retrospectives.

• Developed Book structure engine to automate the net interest margin computational logic.

• Implement drools engine in Book Structure to generate complex logic which includes rate of interest adjustments, Net interest margin computation, matching the credit and savings accounts and loan accounts.

• Developed spark jobs using python and implemented the computational logics using Data Frames and RDD’s.

• Developed HiveQL scripts to create the hive internal and external tables.

• Automated the deployment using Jenkins’s pipeline.

• Used IBM Tivoli batch scheduler to automate the job flow. Systems Engineer June 2016 – August 2017

• Created and deployed windows OS packages and monthly patches in SCCM.

• Performed automation scripts to deploy software upgradations to an existing environment in windows operating server.

• Handled Virtual Machine connectivity through WYSE Thin Clients and VMware View Client.

• Managed Active directory users and computers.

• Administrated Symantec DLO Administrative Server. ACADEMIC PROJECTS

Measuring Attitudes Towards Covid-19 Based on Large-Scale Social Media Analysis

• Multiple experiments have been implemented to analyze the sentiment classification on a large-scale Twitter dataset.

• Collected Tweets using GetOldTweets module and then using LDA and LSA topic modeling Techniques to find top 10 trending topics from whole Dataset.

• Using Machine Learning Models like SVM, Naïve Bayes to find accuracy of the sentiments. Bank Note Authentication

• Implemented Machine learning in bank note application reducing manual load to detect fake bank notes and increased the efficiency of fake note detection.

• Deployed models using Flask and containerized application using Docker.

• Finally, deployed application using Kubernetes.

Data Analysis:

• Implemented a Linear Regression Model using Scikit Learn, Pandas Library in Python on Medical Cost Personal Dataset. Examined the correlation between a person's lifestyle and life characteristics and his or her health insurance costs. In presenting the data there is a relationship between smoking habits and the level of BMI and the level of insurance payment costs and at the model stage achieved 83% accuracy.

• Implemented a K-Nearest Neighbors Model using Scikit Learn, Pandas Library in Python and selected optimum K-value and achieved accuracy of 85% on Famous Iris Dataset.

• Implemented a Logistic Regression Model on Framingham Heart study Dataset. All attributes selected after the elimination process show P-values lower than 5% and thereby suggesting significant role in the Heart disease prediction. Men seem to be more susceptible to heart disease than women. Increase in Age, number of cigarettes smoked per day and systolic Blood Pressure also show increasing odds of having heart disease and at the model stage achieved 88% accuracy. Covid-19 Headlines SPAM Detection:

• Analyzed 9000 user’s headlines dataset to detect weather headline is SPAM or HAM using various Machine Learning Models.

• Cleaned, filtered, transformed data to specific vectorization formation using NLP techniques.

• Evaluated the best technique as Passive Aggressive model using model selection and validated the model using Confusion Matrix, precision-recall curve.

• Predicted the detection system accurately with an estimate of generalized error to be as small as 6%.

• Developed a simple Web Application using “Streamlit” framework to automate the SPAM or HAM detection for end users. Covid-19 Cases and Deaths Prediction:

• Build predictive model for taking better precautions and measures to fight against covid-19 by identifying cases and deaths for next 60-days in USA.

• Performed detailed analysis and insights of data to identify trends for each state in USA.

• Predicted the Covid-19 Cases and Deaths for next 60 days using Prophet predictive model. IMDB Movie Rating Analysis using Tableau:

• Designed a tableau story with different dashboard visualization that depicts Average gross revenue made by each movie and duration by considering director and actor as filters, Genre by revenue, Number of movies per year.

• Created URL action for dashboard for interactivity so that we can open each movie link and created dashboard live action where we can have details about movie, photos, trailer, description etc.

• Developed Tableau data visualization using Cross Map, Scatter Plots, Geographic Map, Pie Charts and Bar Charts, Page Trails, and Density Chart.

Database Systems:

• Developed a “Hospital Management Suite” for managing the inpatient and outpatient services.

• Designed end to end functionalities like Doctors Login, Admin management, Patients Appointment Creation, Patients Appointment management by doctors, Hospital Equipment Management with GUI developed in PHP.

• Implemented CRUD (Create, Read, Update, Delete) functionality for several tables to reflect the stored procedures in MySQL database.

TECHNICAL SKILLS

Programming Languages: Python (Proficient), C++ (Prior Experience), C (prior Experience), HTML, CSS, Java Script Data Bases: MySQL, Oracle

Big Data Technologies: Map Reduce, Sqoop, Hive, Spark, Pig, HBase

Tools: Tableau, Rapid Miner, SaaS, Visual Studio

Cloud Technologies: GCP, Azure

Frameworks: Scikit learn, Pandas, NumPy, Matplotlib, TensorFlow

Relevant Course Work: Machine Learning, Data Analytics, Natural language processing, Deep Learning

Version Control: Git, GitLab

Deployment Pipelines: Jenkins, Kubernetes



Contact this candidate